ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
This work proposes a new paradigm for monocular depth estimation that explicitly models the hierarchical structure of scene geometry, addressing a key limitation of diffusion models for geometric tasks.
ARDepth introduces an auto-regressive framework for monocular depth estimation that progressively constructs depth representations across spatial scales, achieving strong performance and structurally consistent predictions. The method outperforms diffusion-based approaches in capturing fine-grained local details while maintaining global coherence.
Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE). However, they implicitly assume that depth can be recovered as a globally smooth field through iterative denoising, which does not explicitly reflect the piecewise and scale-dependent organization of scene geometry. In practice, geometric structure emerges progressively across spatial scales, where coarse layout, surfaces, and boundaries are constructed in a hierarchical manner. Motivated by this observation, we introduce ARDepth, which formulates depth estimation as structured auto-regressive generation. Instead of recovering depth through global refinement, ARDepth progressively constructs depth representations as spatial resolution increases. To support this generative process, we introduce Scale-Progressive Conditioning (SPC) to inject multi-scale visual features at each generation stage, and Semantic-Aware Guidance (SAG) to provide scene-level semantic priors that enhance global structural consistency. Together, these designs enable the model to capture fine-grained local details while maintaining coherent global geometry. Empirical results demonstrate that our approach achieves strong performance and produces structurally consistent depth predictions across scales, validating auto-regressive generation as a promising alternative paradigm for geometric modeling.